SAM3 - Promptable Concept Segmentation (PCS)

SAM3 performs zero-shot instance segmentation using natural language prompts. Upload an image, enter a text prompt (e.g., "person", "car", "dog"), and get segmentation masks.

Built with anycoder

Inputs

Input Image

Output (Segmented Image)

Text Prompt

Detection Threshold

Higher = fewer detections

0 1

Mask Threshold

Higher = sharper masks

0 1

📝 Enter a prompt and click Segment to start.

Examples

Input Image	Text Prompt

Notes

Model: facebook/sam3
Click on segments in the output to see labels
GPU recommended for faster inference